Logo
Loading...
期刊
专家
GAIR Live
热门文章
AI Infra
北大王选所彭宇新团队:让多模态大模型学会「看懂物种关系」丨CVPR 2026
TARA:融合生物知识与视觉特征,提升模型推理能力。 作者丨郑佳美 编辑丨岑 峰 近年来,多模态大模型的发展正在不断推动视觉理解能力的提升。从图像分类、目标检测到视觉问答等任务,视觉系统已经能够在多种场景中实现较高水平的识别和推理能力。然而,在更复杂的层级视觉识别任务中,现有模型仍然存在明显不足。 现实世界中的许多视觉概念天然具有层级结构,例如生物分类体系中的“界 — 门 — 纲 — 目 — 科 — 属 — 种”,以及商品分类、医学诊断等领域中的多层级标签体系。这类任务不仅要求模型识别具体类别,还需要理解不同类别之间的层级关系和语义结构。但目前多数视觉模型仍然基于扁平分类框架进行训练,在进行层级预测时容易出现分类路径不一致或层级关系冲突等问题。 与此同时,在开放世界环境中,视觉模型还需要具备识别未知类别的能力。以生物识别任务为例,现实世界中的物种数量远远超过现有数据集的覆盖范围,新的物种仍在不断被发现。 当模型面对训练数据中未出现的类别时,往往难以进行合理推断。如何利用已有知识帮助模型理解类别之间的层级结构,并在有限数据条件下推断未知类别,逐渐成为当前视觉智能研究中的重要问题。...
GAIR DAO
2026-03-11
全部文章
热门视频
全部视频
人气专家
安波 President's Chair Professor College of Computing and Data Science Nanyang Technological University, Head, Division of Artificial Intelligence, College of Computing & Data Science, President’s Chair in Computer Science and Engineering, Professor, College of Computing & Data Science, Assistant Chair (Innovation), School of Computer Science and Engineering (SCSE)
Bo An is a Professor in the College of Computing & Data Science, and Co-Director of Artificial Intelligence Research Institute (AI.R) at Nanyang Technological University, Singapore. He received the Ph.D degree in Computer Science from the University of Massachusetts, Amherst. His current research interests include artificial intelligence, multiagent systems, computational game theory, reinforcement learning, and optimization. His research results have been successfully applied to many domains including infrastructure security and e-commerce. He has published over 100 referred papers at AAMAS, IJCAI, AAAI, ICAPS, KDD, UAI, EC, WWW, ICLR, NeurIPS, ICML, JAAMAS, AIJ and ACM/IEEE Transactions. Dr. An was the recipient of the 2010 IFAAMAS Victor Lesser Distinguished Dissertation Award, an Operational Excellence Award from the Commander, First Coast Guard District of the United States, the 2012 INFORMS Daniel H. Wagner Prize for Excellence in Operations Research Practice, and 2018 Nanyang Research Award (Young Investigator). His publications won the Best Innovative Application Paper Award at AAMAS’12, the Innovative Application Award at IAAI’16, and the best paper award at DAI’20. He was invited to give Early Career Spotlight talk at IJCAI’17. He led the team HogRider which won the 2017 Microsoft Collaborative AI Challenge. He was named to IEEE Intelligent Systems' "AI's 10 to Watch" list for 2018. He is PC Co-Chair of AAMAS’20 and will be General Co-Chair of AAMAS’23. He is a member of the editorial board of JAIR and is the Associate Editor of AIJ, JAAMAS, IEEE Intelligent Systems, ACM TAAS, and ACM TIST. He was elected to the board of directors of IFAAMAS, senior member of AAAI, and Distinguished member of ACM.